test/jalview/ext/ensembl/EnsemblCdnaTest.java

   1 /*
   2  * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
   3  * Copyright (C) $$Year-Rel$$ The Jalview Authors
   4  *
   5  * This file is part of Jalview.
   6  *
   7  * Jalview is free software: you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License
   9  * as published by the Free Software Foundation, either version 3
  10  * of the License, or (at your option) any later version.
  11  *
  12  * Jalview is distributed in the hope that it will be useful, but
  13  * WITHOUT ANY WARRANTY; without even the implied warranty
  14  * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
  15  * PURPOSE.  See the GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
  19  * The Jalview Authors are detailed in the 'AUTHORS' file.
  20  */
  21 package jalview.ext.ensembl;
  22
  23 import static org.testng.AssertJUnit.assertEquals;
  24 import static org.testng.AssertJUnit.assertFalse;
  25 import static org.testng.AssertJUnit.assertNull;
  26 import static org.testng.AssertJUnit.assertTrue;
  27
  28 import jalview.datamodel.SequenceDummy;
  29 import jalview.datamodel.SequenceFeature;
  30 import jalview.datamodel.SequenceI;
  31 import jalview.gui.JvOptionPane;
  32 import jalview.io.gff.SequenceOntologyFactory;
  33 import jalview.io.gff.SequenceOntologyLite;
  34 import jalview.util.MapList;
  35
  36 import java.util.List;
  37
  38 import org.testng.Assert;
  39 import org.testng.annotations.AfterClass;
  40 import org.testng.annotations.BeforeClass;
  41 import org.testng.annotations.Test;
  42
  43 public class EnsemblCdnaTest
  44 {
  45
  46   @BeforeClass(alwaysRun = true)
  47   public void setUpJvOptionPane()
  48   {
  49     JvOptionPane.setInteractiveMode(false);
  50     JvOptionPane.setMockResponse(JvOptionPane.CANCEL_OPTION);
  51   }
  52
  53   @BeforeClass(alwaysRun = true)
  54   public void setUp()
  55   {
  56     SequenceOntologyFactory.setInstance(new SequenceOntologyLite());
  57   }
  58
  59   @AfterClass(alwaysRun = true)
  60   public void tearDown()
  61   {
  62     SequenceOntologyFactory.setInstance(null);
  63   }
  64
  65   /**
  66    * Test that the cdna part of genomic sequence is correctly identified by
  67    * 'exon' features (or subtypes) - reverse strand case.
  68    */
  69   @Test(groups = "Functional")
  70   public void testGetGenomicRangesFromFeatures_reverseStrand()
  71   {
  72     EnsemblCdna testee = new EnsemblCdna();
  73     SequenceI genomic = new SequenceDummy("chr7");
  74     genomic.setStart(10000);
  75     genomic.setEnd(50000);
  76     String transcriptId = "ABC123";
  77
  78     // exon at (start+10000) length 501
  79     SequenceFeature sf = new SequenceFeature("exon", "", 20000, 20500, 0f,
  80             null);
  81     sf.setValue("Parent", "transcript:" + transcriptId);
  82     sf.setStrand("-");
  83     genomic.addSequenceFeature(sf);
  84
  85     // exon (sub-type) at (start + exon_variant) length 101
  86     sf = new SequenceFeature("coding_exon", "", 10500, 10600, 0f, null);
  87     sf.setValue("Parent", "transcript:" + transcriptId);
  88     sf.setStrand("-");
  89     genomic.addSequenceFeature(sf);
  90
  91     // exon belonging to a different transcript doesn't count
  92     sf = new SequenceFeature("exon", "", 11500, 12600, 0f, null);
  93     sf.setValue("Parent", "transcript:anotherOne");
  94     genomic.addSequenceFeature(sf);
  95
  96     // transcript feature doesn't count
  97     sf = new SequenceFeature("transcript", "", 10000, 50000, 0f, null);
  98     genomic.addSequenceFeature(sf);
  99
 100     MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
 101             transcriptId, 23);
 102     List<int[]> fromRanges = ranges.getFromRanges();
 103     assertEquals(2, fromRanges.size());
 104
 105     /*
 106      * from ranges should be sorted by start order descending
 107      * and hold mappings from reverse strand sense
 108      */
 109     assertEquals(20500, fromRanges.get(0)[0]);
 110     assertEquals(20000, fromRanges.get(0)[1]);
 111     assertEquals(10600, fromRanges.get(1)[0]);
 112     assertEquals(10500, fromRanges.get(1)[1]);
 113     // to range should start from given start numbering
 114     List<int[]> toRanges = ranges.getToRanges();
 115     assertEquals(1, toRanges.size());
 116     assertEquals(23, toRanges.get(0)[0]);
 117     assertEquals(624, toRanges.get(0)[1]);
 118   }
 119
 120   /**
 121    * Test that the cdna part of genomic sequence is correctly identified by
 122    * 'exon' features (or subtypes) with the desired transcript as parent
 123    */
 124   @Test(groups = "Functional")
 125   public void testGetGenomicRangesFromFeatures()
 126   {
 127     EnsemblCdna testee = new EnsemblCdna();
 128     SequenceI genomic = new SequenceDummy("chr7");
 129     genomic.setStart(10000);
 130     genomic.setEnd(50000);
 131     String transcriptId = "ABC123";
 132
 133     // exon at (start+10000) length 501
 134     SequenceFeature sf = new SequenceFeature("exon", "", 20000, 20500, 0f,
 135             null);
 136     sf.setValue("Parent", "transcript:" + transcriptId);
 137     sf.setStrand("+");
 138     genomic.addSequenceFeature(sf);
 139
 140     // exon (sub-type) at (start + exon_variant) length 101
 141     sf = new SequenceFeature("coding_exon", "", 10500, 10600, 0f, null);
 142     sf.setValue("Parent", "transcript:" + transcriptId);
 143     sf.setStrand("+");
 144     genomic.addSequenceFeature(sf);
 145
 146     // exon belonging to a different transcript doesn't count
 147     sf = new SequenceFeature("exon", "", 11500, 12600, 0f, null);
 148     sf.setValue("Parent", "transcript:anotherOne");
 149     genomic.addSequenceFeature(sf);
 150
 151     // transcript feature doesn't count
 152     sf = new SequenceFeature("transcript", "", 10000, 50000, 0f, null);
 153     sf.setStrand("-"); // weird but ignored
 154     genomic.addSequenceFeature(sf);
 155
 156     MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
 157             transcriptId, 23);
 158     List<int[]> fromRanges = ranges.getFromRanges();
 159     assertEquals(2, fromRanges.size());
 160     // from ranges should be sorted by start order
 161     assertEquals(10500, fromRanges.get(0)[0]);
 162     assertEquals(10600, fromRanges.get(0)[1]);
 163     assertEquals(20000, fromRanges.get(1)[0]);
 164     assertEquals(20500, fromRanges.get(1)[1]);
 165     // to range should start from given start numbering
 166     List<int[]> toRanges = ranges.getToRanges();
 167     assertEquals(1, toRanges.size());
 168     assertEquals(23, toRanges.get(0)[0]);
 169     assertEquals(624, toRanges.get(0)[1]);
 170   }
 171
 172   /**
 173    * The method under test should give up and return null if both forward and
 174    * reverse strands are present in the features of interest
 175    */
 176   @Test(groups = "Functional")
 177   public void testGetGenomicRangesFromFeatures_mixedStrand()
 178   {
 179     EnsemblCdna testee = new EnsemblCdna();
 180     SequenceI genomic = new SequenceDummy("chr7");
 181     genomic.setStart(10000);
 182     genomic.setEnd(50000);
 183     String transcriptId = "ABC123";
 184
 185     SequenceFeature sf = new SequenceFeature("exon", "", 20000, 20500, 0f,
 186             null);
 187     sf.setValue("Parent", "transcript:" + transcriptId);
 188     sf.setStrand("-");
 189     genomic.addSequenceFeature(sf);
 190
 191     sf = new SequenceFeature("coding_exon", "", 10500, 10600, 0f, null);
 192     sf.setValue("Parent", "transcript:" + transcriptId);
 193     sf.setStrand("+");
 194     genomic.addSequenceFeature(sf);
 195
 196     MapList ranges = testee.getGenomicRangesFromFeatures(genomic,
 197             transcriptId, 23);
 198     assertNull(ranges);
 199   }
 200
 201   /**
 202    * Test the method that retains features except for 'transcript' (or
 203    * subtypes), or features with parent other than the given id
 204    */
 205   @Test(groups = "Functional")
 206   public void testRetainFeature()
 207   {
 208     String accId = "ABC123";
 209     EnsemblCdna testee = new EnsemblCdna();
 210
 211     SequenceFeature sf = new SequenceFeature("transcript", "", 20000,
 212             20500, 0f, null);
 213     assertFalse(testee.retainFeature(sf, accId));
 214
 215     sf = new SequenceFeature("aberrant_processed_transcript", "", 20000,
 216             20500, 0f, null);
 217     assertFalse(testee.retainFeature(sf, accId));
 218
 219     sf = new SequenceFeature("NMD_transcript_variant", "", 20000, 20500,
 220             0f, null);
 221     assertFalse(testee.retainFeature(sf, accId));
 222
 223     // other feature with no parent is retained
 224     sf = new SequenceFeature("sequence_variant", "", 20000, 20500, 0f, null);
 225     assertTrue(testee.retainFeature(sf, accId));
 226
 227     // other feature with desired parent is retained
 228     sf.setValue("Parent", "transcript:" + accId);
 229     assertTrue(testee.retainFeature(sf, accId));
 230
 231     // test is not case-sensitive
 232     assertTrue(testee.retainFeature(sf, accId.toLowerCase()));
 233
 234     // feature with wrong parent is not retained
 235     sf.setValue("Parent", "transcript:XYZ");
 236     assertFalse(testee.retainFeature(sf, accId));
 237   }
 238
 239   /**
 240    * Test the method that picks out 'exon' (or subtype) features with the
 241    * accession id as parent
 242    */
 243   @Test(groups = "Functional")
 244   public void testIdentifiesSequence()
 245   {
 246     String accId = "ABC123";
 247     EnsemblCdna testee = new EnsemblCdna();
 248
 249     // exon with no parent not valid
 250     SequenceFeature sf = new SequenceFeature("exon", "", 1, 2, 0f, null);
 251     assertFalse(testee.identifiesSequence(sf, accId));
 252
 253     // exon with wrong parent not valid
 254     sf.setValue("Parent", "transcript:XYZ");
 255     assertFalse(testee.identifiesSequence(sf, accId));
 256
 257     // exon with right parent is valid
 258     sf.setValue("Parent", "transcript:" + accId);
 259     assertTrue(testee.identifiesSequence(sf, accId));
 260
 261     // exon sub-type with right parent is valid
 262     sf = new SequenceFeature("coding_exon", "", 1, 2, 0f, null);
 263     sf.setValue("Parent", "transcript:" + accId);
 264     assertTrue(testee.identifiesSequence(sf, accId));
 265
 266     // transcript not valid:
 267     sf = new SequenceFeature("transcript", "", 1, 2, 0f, null);
 268     sf.setValue("Parent", "transcript:" + accId);
 269     assertFalse(testee.identifiesSequence(sf, accId));
 270
 271     // CDS not valid:
 272     sf = new SequenceFeature("CDS", "", 1, 2, 0f, null);
 273     sf.setValue("Parent", "transcript:" + accId);
 274     assertFalse(testee.identifiesSequence(sf, accId));
 275   }
 276
 277   @Test(groups = "Functional")
 278   public void testIsValidReference() throws Exception
 279   {
 280     EnsemblSequenceFetcher esq = new EnsemblCdna();
 281     Assert.assertTrue(esq.isValidReference("CCDS5863.1"));
 282     Assert.assertTrue(esq.isValidReference("ENST00000288602"));
 283     Assert.assertTrue(esq.isValidReference("ENSG00000288602"));
 284     Assert.assertFalse(esq.isValidReference("ENSP00000288602"));
 285     Assert.assertFalse(esq.isValidReference("ENST0000288602"));
 286     // non-human species having a 3 character identifier included:
 287     Assert.assertTrue(esq.isValidReference("ENSMUSG00000099398"));
 288   }
 289 }